{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/sft/papers/5","list_of":"/method/sft","method":"SFT","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":5,"pages_in_order":5,"rows_per_page":100,"rows":[401,415],"of":415,"counts":{"archive_papers_tagged":415,"with_a_code_link":204,"where_syntology_ran_a_sample":103,"not_listed_spam_title":0,"listed":415,"listed_where_code_ran":103,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":86,"every_run_a_failure_of_syntologys_instrument":17,"listed_with_a_run_with_no_instrument_failure":86,"listed_every_run_a_failure_of_syntologys_instrument":17,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/sft","prev":"/method/sft/papers/4","next":null,"papers":[{"paper":"/paper/instag-instruction-tagging-for-diversity-and","slug":"instag-instruction-tagging-for-diversity-and","title":"#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models","date":"2023-08-14","arxiv_id":"2308.07074","n_code_links":1,"syntology":null},{"paper":"/paper/zhongjing-enhancing-the-chinese-medical","slug":"zhongjing-enhancing-the-chinese-medical","title":"Zhongjing: Enhancing the Chinese Medical Capabilities of Large Language Model through Expert Feedback and Real-world Multi-turn Dialogue","date":"2023-08-07","arxiv_id":"2308.03549","n_code_links":1,"syntology":null},{"paper":"/paper/okapi-instruction-tuned-large-language-models","slug":"okapi-instruction-tuned-large-language-models","title":"Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback","date":"2023-07-29","arxiv_id":"2307.16039","n_code_links":2,"syntology":{"ran":8,"of":11,"n_ran_checked":7,"n_instrument":1,"unverified":3,"pointer_only":7,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["nlp-uoregon/okapi"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"mediagpt-a-large-language-model-target","title":"MediaGPT : A Large Language Model For Chinese Media","date":"2023-07-20","arxiv_id":"2307.10930","n_code_links":0,"syntology":null},{"paper":"/paper/secrets-of-rlhf-in-large-language-models-part","slug":"secrets-of-rlhf-in-large-language-models-part","title":"Secrets of RLHF in Large Language Models Part I: PPO","date":"2023-07-11","arxiv_id":"2307.04964","n_code_links":1,"syntology":null},{"paper":"/paper/preference-ranking-optimization-for-human","slug":"preference-ranking-optimization-for-human","title":"Preference Ranking Optimization for Human Alignment","date":"2023-06-30","arxiv_id":"2306.17492","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-uses-of-large-language-models-to","title":"On the Uses of Large Language Models to Interpret Ambiguous Cyberattack Descriptions","date":"2023-06-24","arxiv_id":"2306.14062","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-language-models-with-generative","title":"Fine-tuning Language Models with Generative Adversarial Reward Modelling","date":"2023-05-09","arxiv_id":"2305.06176","n_code_links":0,"syntology":null},{"paper":"/paper/rrhf-rank-responses-to-align-language-models","slug":"rrhf-rank-responses-to-align-language-models","title":"RRHF: Rank Responses to Align Language Models with Human Feedback without tears","date":"2023-04-11","arxiv_id":"2304.05302","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ganjinzero/rrhf"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/sft-kd-recon-learning-a-student-friendly","slug":"sft-kd-recon-learning-a-student-friendly","title":"SFT-KD-Recon: Learning a Student-friendly Teacher for Knowledge Distillation in Magnetic Resonance Image Reconstruction","date":"2023-04-11","arxiv_id":"2304.05057","n_code_links":1,"syntology":null},{"paper":"/paper/optimizing-ddpm-sampling-with-shortcut-fine","slug":"optimizing-ddpm-sampling-with-shortcut-fine","title":"Optimizing DDPM Sampling with Shortcut Fine-Tuning","date":"2023-01-31","arxiv_id":"2301.13362","n_code_links":1,"syntology":{"ran":4,"of":9,"n_ran_checked":2,"n_instrument":2,"unverified":5,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["uw-madison-lee-lab/sft-pg"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/self-filtering-a-noise-aware-sample-selection","slug":"self-filtering-a-noise-aware-sample-selection","title":"Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalization","date":"2022-08-24","arxiv_id":"2208.11351","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["1998v7/self-filtering"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"cognitive-modeling-of-semantic-fluency-using","title":"Cognitive Modeling of Semantic Fluency Using Transformers","date":"2022-08-20","arxiv_id":"2208.09719","n_code_links":0,"syntology":null},{"paper":null,"slug":"p-adic-statistical-field-theory-and-deep","title":"p-Adic Statistical Field Theory and Deep Belief Networks","date":"2022-07-28","arxiv_id":"2207.13877","n_code_links":0,"syntology":null},{"paper":"/paper/pre-trained-summarization-distillation","slug":"pre-trained-summarization-distillation","title":"Pre-trained Summarization Distillation","date":"2020-10-24","arxiv_id":"2010.13002","n_code_links":1,"syntology":null}],"record_sha256":"f4f5395ec0ce40523ce46dd8c4c0272d525d742e70444c46a42c517949712559","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}